update_metadata

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states a destructive side effect: 'other keys are dropped,' meaning any keys not in the allowlist will be discarded. This is valuable beyond simply saying 'Update.' However, it does not mention behavior around expected_hash, permissions, or reversibility, but the dropping detail is the most critical.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. Every phrase carries information: 'allowlisted set' scopes the operation, enumerates example fields, and the final clause discloses the destructive behavior. There is zero redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter mutation tool with no annotations and no output schema, the description is too sparse. It does not clarify what 'note' refers to (ID, path, content), the purpose or format of 'expected_hash,' or the exact semantics of the allowlisting (e.g., are existing allowlisted fields preserved if absent from 'fields'?). An agent would need to make assumptions to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It provides some semantics for the 'fields' parameter by listing example allowlisted keys (status/tags/agent_generated) and noting non-allowlisted keys are dropped. But it does not explain the 'note' parameter or the 'expected_hash' parameter (likely a concurrency guard), leaving the agent to guess their meaning and use.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Update') and resource ('frontmatter fields'), and clarifies the scope with 'allowlisted set' and 'other keys are dropped.' This clearly distinguishes it from siblings like move_note, append_note, or archive_notes, which operate on different aspects of a note.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any guidance on when to use this tool versus alternatives, does not mention prerequisites, and offers no explicit exclusions or alternative tool names. It only states what the tool does, leaving the agent to infer when it is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.